Skeleton-based action recognition with low-level features of adaptive graph convolutional networks

HIGHLIGHTS

• who: . and collaborators from the (UNIVERSITY) have published the paper: Skeleton-Based Action Recognition with Low-Level Features of Adaptive Graph Convolutional Networks, in the Journal: (JOURNAL)
• what: The first reason is that the experience of CNN shows low-level information is also critical for classification . Based on both considerations, the authors propose a novel framework taking advantage of global lowlevel features based on . The main contributions of the work lie in three aspects: A human action recognition framework with a multibranches structure is proposed to learn the low-level features of skeleton data. Idea . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.